ComfyUI

Author	SHA1	Message	Date
comfyanonymous	f81a6fade8	Fix some edge cases with samplers and arrays with a single sigma.	7 months ago
Jedrzej Kosinski	7990ae18c1	Fix error when more cond masks passed in than batch size (#3353 )	7 months ago
comfyanonymous	0f5768e038	Fix missing arguments in cfg_function.	8 months ago
comfyanonymous	1a0486bb96	Fix model needing to be loaded on GPU to generate the sigmas.	8 months ago
comfyanonymous	c6bd456c45	Make zero denoise a NOP.	8 months ago
comfyanonymous	fcfd2bdf8a	Small cleanup.	8 months ago
comfyanonymous	0542088ef8	Refactor sampler code for more advanced sampler nodes part 2.	8 months ago
comfyanonymous	57753c964a	Refactor sampling code for more advanced sampler nodes.	8 months ago
comfyanonymous	e6482fbbfc	Refactor calc_cond_uncond_batch into calc_cond_batch. calc_cond_batch can take an arbitrary amount of cond inputs. Added a calc_cond_uncond_batch wrapper with a warning so custom nodes won't break.	8 months ago
comfyanonymous	0624838237	Add inverse noise scaling function.	8 months ago
comfyanonymous	f2fe635c9f	SamplerDPMAdaptative node to test the different options.	8 months ago
comfyanonymous	2a813c3b09	Switch some more prints to logging.	8 months ago
comfyanonymous	12c1080ebc	Simplify differential diffusion code.	9 months ago
Shiimizu	727021bdea	Implement Differential Diffusion (#2876 ) * Implement Differential Diffusion * Cleanup. * Fix. * Masks should be applied at full strength. * Fix colors. * Register the node. * Cleaner code. * Fix issue with getting unipc sampler. * Adjust thresholds. * Switch to linear thresholds. * Only calculate nearest_idx on valid thresholds.	9 months ago
comfyanonymous	00425563c0	Cleanup: Use sampling noise scaling function for inpainting.	9 months ago
comfyanonymous	c62e836167	Move noise scaling to object with sampling math.	9 months ago
comfyanonymous	d46583ecec	Playground V2.5 support with ModelSamplingContinuousEDM node. Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.	9 months ago
logtd	e1cb93c383	Fix model and cond transformer options merge	9 months ago
comfyanonymous	10847dfafe	Cleanup uni_pc inpainting. This causes some small changes to the uni pc inpainting behavior but it seems to improve results slightly.	9 months ago
Jedrzej Kosinski	f44225fd5f	Fix infinite while loop being possible in ddim_scheduler	9 months ago
blepping	a352c021ec	Allow custom samplers to request discard penultimate sigma	9 months ago
comfyanonymous	89507f8adf	Remove some unused imports.	10 months ago
Dr.Lt.Data	05cd00695a	typo fix - calculate_sigmas_scheduler (#2619 ) self.scheduler -> scheduler_name Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>	10 months ago
comfyanonymous	8c6493578b	Implement noise augmentation for SD 4X upscale model.	11 months ago
comfyanonymous	9a7619b72d	Fix regression with inpaint model.	11 months ago
comfyanonymous	571ea8cdcc	Fix SAG not working with cfg 1.0	11 months ago
comfyanonymous	8cf1daa108	Fix SDXL area composition sometimes not using the right pooled output.	11 months ago
Hari	574363a8a6	Implement Perp-Neg	11 months ago
comfyanonymous	329c571993	Improve code legibility.	11 months ago
comfyanonymous	6c5990f7db	Fix cfg being calculated more than once if sampler_cfg_function.	11 months ago
comfyanonymous	ba04a87d10	Refactor and improve the sag node. Moved all the sag related code to comfy_extras/nodes_sag.py	11 months ago
Rafie Walker	6761233e9d	Implement Self-Attention Guidance (#2201 ) * First SAG test * need to put extra options on the model instead of patcher * no errors and results seem not-broken * Use @ashen-uncensored formula, which works better!!! * Fix a crash when using weird resolutions. Remove an unnecessary UNet call * Improve comments, optimize memory in blur routine * SAG works with sampler_cfg_function	11 months ago
comfyanonymous	97015b6b38	Cleanup.	12 months ago
comfyanonymous	dcec1047e6	Invert the start and end percentages in the code. This doesn't affect how percentages behave in the frontend but breaks things if you relied on them in the backend. percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion. Make percent 0 return an extremely large sigma and percent 1.0 return a zero one to fix imprecision.	1 year ago
comfyanonymous	57eea0efbb	heunpp2 sampler.	1 year ago
comfyanonymous	420beeeb05	Clean up and refactor sampler code. This should make it much easier to write custom nodes with kdiffusion type samplers.	1 year ago
comfyanonymous	dd4ba68b6e	Allow different models to estimate memory usage differently.	1 year ago
comfyanonymous	2c9dba8dc0	sampling_function now has the model object as the argument.	1 year ago
comfyanonymous	8d80584f6a	Remove useless argument from uni_pc sampler.	1 year ago
comfyanonymous	58d5d71a93	Working RescaleCFG node. This was broken because of recent changes so I fixed it and moved it from the experiments repo.	1 year ago
comfyanonymous	002aefa382	Support lcm models. Use the "lcm" sampler to sample them, you also have to use the ModelSamplingDiscrete node to set them as lcm models to use them properly.	1 year ago
comfyanonymous	ae2acfc21b	Don't convert Nan to zero. Converting Nan to zero is a bad idea because it makes it hard to tell when something went wrong.	1 year ago
comfyanonymous	d2e27b48f1	sampler_cfg_function now gets the noisy output as argument again. This should make things that use sampler_cfg_function behave like before. Added an input argument for those that want the denoised output. This means you can calculate the x0 prediction of the model by doing: (input - cond) for example.	1 year ago
comfyanonymous	e73ec8c4da	Not used anymore.	1 year ago
comfyanonymous	111f1b5255	Fix some issues with sampling precision.	1 year ago
comfyanonymous	7c0f255de1	Clean up percent start/end and make controlnets work with sigmas.	1 year ago
comfyanonymous	a268a574fa	Remove a bunch of useless code. DDIM is the same as euler with a small difference in the inpaint code. DDIM uses randn_like but I set a fixed seed instead. I'm keeping it in because I'm sure if I remove it people are going to complain.	1 year ago
comfyanonymous	1777b54d02	Sampling code changes. apply_model in model_base now returns the denoised output. This means that sampling_function now computes things on the denoised output instead of the model output. This should make things more consistent across current and future models.	1 year ago
comfyanonymous	036f88c621	Refactor to make it easier to add custom conds to models.	1 year ago
comfyanonymous	3fce8881ca	Sampling code refactor to make it easier to add more conds.	1 year ago

1 2 3

136 Commits (master)